Related papers: Target-Distribution-Guided Cross-Functional Fine-T…

Titanium and its alloys are technologically important materials that display a rich phase behaviour. In order to enable large-scale, realistic modelling of Ti and its alloys on the atomistic scale, Machine Learning Interatomic Potentials…

Foundational machine learning interatomic potentials (MLIPs) are being developed at a rapid pace, promising closer and closer approximation to ab initio accuracy. This unlocks the possibility to simulate much larger length and time scales.…

To address the trade-off problem of quality-diversity for the generated images in imbalanced classification tasks, we research on over-sampling based methods at the feature level instead of the data level and focus on searching the latent…

Diffusion models are widely used for generative tasks across domains. Given a pre-trained diffusion model, it is often desirable to fine-tune it further either to correct for errors in learning or to align with downstream applications.…

Machine-learned interatomic potentials (MLIPs) are becoming an essential tool in materials modeling. However, optimizing the generation of training data used to parameterize the MLIPs remains a significant challenge. This is because MLIPs…

The probabilistic diffusion model (DM), generating content by inferencing through a recursive chain structure, has emerged as a powerful framework for visual generation. After pre-training on enormous data, the model needs to be properly…

Conventional multi-label classification (MLC) methods assume that all samples are fully labeled and identically distributed. Unfortunately, this assumption is unrealistic in large-scale MLC data that has long-tailed (LT) distribution and…

Many machine learning models appear to deploy effortlessly under distribution shift, and perform well on a target distribution that is considerably different from the training distribution. Yet, learning theory of distribution shift bounds…

Subpopulation shift exists widely in many real-world applications, which refers to the training and test distributions that contain the same subpopulation groups but with different subpopulation proportions. Ignoring subpopulation shifts…

We study multilabel classification of chest X-rays and present a simple, strong pipeline built on SE-ResNeXt101 $(32 \times 4d)$. The backbone is finetuned for 14 thoracic findings with a sigmoid head, trained using Multilabel Iterative…

Multi-Task Learning (MTL) aims to boost predictive performance by sharing information across related tasks, yet conventional methods often suffer from negative transfer when unrelated or noisy tasks are forced to share representations. We…

Imitation learning (IL) enables autonomous behavior by learning from expert demonstrations. While more sample-efficient than comparative alternatives like reinforcement learning, IL is sensitive to compounding errors induced by distribution…

Industrial surface defect inspection for sample-wise quality control (QC) must simultaneously decide whether a given sample contains defects and localize those defects spatially. In real production lines, extreme foreground-background…

Multimodal Large Language Model (MLLM) have demonstrated strong generalization capabilities across diverse distributions and tasks, largely due to extensive pre-training datasets. Fine-tuning MLLM has become a common practice to improve…

Integrating machine learning into reactive chemistry, materials discovery, and drug design is revolutionizing the development of novel molecules and materials. Machine Learning Interatomic Potentials (MLIPs) accurately predict energies and…

Preference alignment methods are increasingly critical for steering large language models (LLMs) to generate outputs consistent with human values. While recent approaches often rely on synthetic data generated by LLMs for scalability and…

Effective resource management plays a pivotal role in wireless networks, which, unfortunately, results in challenging mixed-integer nonlinear programming (MINLP) problems in most cases. Machine learning-based methods have recently emerged…

Multi-task learning (MTL) for dense prediction has shown promising results but still faces challenges in balancing shared representations with task-specific specialization. In this paper, we introduce a novel Fine-Grained Mixture of Experts…

We improve the recently-proposed "MixMatch" semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring. Distribution alignment encourages the marginal distribution of predictions…

The visual models pretrained on large-scale benchmarks encode general knowledge and prove effective in building more powerful representations for downstream tasks. Most existing approaches follow the fine-tuning paradigm, either by…